apptt.py

import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
from shapely.geometry import Polygon, box as shapely_box
import subprocess
import gradio as gr
# ... (previous functions remain unchanged)


def extract_class_0_coordinates(filename):
    class_0_coordinates = []
    current_class = None
    
    with open(filename, 'r') as file:
          
        for line in file:
            parts = line.strip().split()
            if len(parts) == 0:
                continue
            
            if parts[0] == '0':
                coordinates = [float(x) for x in parts[1:]]
                class_0_coordinates.extend(coordinates)
    
    return class_0_coordinates

def run_yolo_models1(img):
    # Run YOLOv9 segmentation
    os.system(f"python segment/predict.py --source {img} --img 640 --device cpu --weights models/segment/best-2.pt --name yolov9_c_640_detect --exist-ok --save-txt")

    # Run YOLOv9 detection
    os.system(f"python detect.py --source {img} --img 640 --device cpu --weights models/detect/yolov9-s-converted.pt --name yolov9_c_640_detect --exist-ok --save-txt")

def parse_yolo_box(box_string):
    """Parse a YOLO format bounding box string."""
    values = list(map(float, box_string.split()))
    if len(values) < 5:
        raise ValueError(f"Expected at least 5 values, got {len(values)}")
    return values[0], values[1], values[2], values[3], values[4]


def read_yolo_boxes(file_path):
    boxes = []
    with open(file_path, 'r') as f:
        for line in f:
            parts = line.strip().split()
            class_name = COCO_CLASSES[int(parts[0])]
            x, y, w, h = map(float, parts[1:5])
            boxes.append((class_name, x, y, w, h))
    return boxes

def yolo_to_pixel_coord(x, y, img_width, img_height):
    """Convert a single YOLO coordinate to pixel coordinate."""
    return int(x * img_width), int(y * img_height)


def yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height):
    """Convert YOLO format coordinates to pixel coordinates."""
    x1 = int((x_center - width / 2) * img_width)
    y1 = int((y_center - height / 2) * img_height)
    x2 = int((x_center + width / 2) * img_width)
    y2 = int((y_center + height / 2) * img_height)
    return x1, y1, x2, y2

def box_segment_relationship(yolo_box, segment, img_width, img_height, threshold):
    """Check the relationship between a bounding box and a segmented area."""
    class_id, x_center, y_center, width, height = yolo_box
    x1, y1, x2, y2 = yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height)
    pixel_segment = convert_segment_to_pixel(segment, img_width, img_height)
    segment_polygon = Polygon(zip(pixel_segment[::2], pixel_segment[1::2]))
    box_polygon = shapely_box(x1, y1, x2, y2)
    
    if box_polygon.intersects(segment_polygon):
        return "intersecting"
    elif box_polygon.distance(segment_polygon) <= threshold:
        return "obstructed"
    else:
        return "not touching"
def convert_segment_to_pixel(segment, img_width, img_height):
    """Convert segment coordinates from YOLO format to pixel coordinates."""
    pixel_segment = []
    for i in range(0, len(segment), 2):
        x, y = yolo_to_pixel_coord(segment[i], segment[i+1], img_width, img_height)
        pixel_segment.extend([x, y])
    return pixel_segment

def plot_boxes_and_segment(image, yolo_boxes, segment, img_width, img_height, threshold):
    """Plot the image with intersecting boxes, obstructed boxes, and segment."""
    fig, ax = plt.subplots(figsize=(12, 8))
    ax.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    
    pixel_segment = convert_segment_to_pixel(segment, img_width, img_height)
    ax.plot(pixel_segment[::2] + [pixel_segment[0]], pixel_segment[1::2] + [pixel_segment[1]], 'g-', linewidth=2, label='Rail Zone')
    
    colors = {'intersecting': 'r', 'obstructed': 'y', 'not touching': 'b'}
    labels = {'intersecting': 'Intersecting Box', 'obstructed': 'Obstructed Box', 'not touching': 'Non-interacting Box'}
    
    for yolo_box in yolo_boxes:
        class_id, x_center, y_center, width, height = yolo_box
        x1, y1, x2, y2 = yolo_to_pixel_coords(x_center, y_center, width, height, img_width, img_height)
        relationship = box_segment_relationship(yolo_box, segment, img_width, img_height, threshold)
        color = colors[relationship]
        label = labels[relationship]
        ax.add_patch(plt.Rectangle((x1, y1), x2-x1, y2-y1, fill=False, edgecolor=color, linewidth=2, label=label))
    
    ax.legend()
    ax.axis('off')
    plt.tight_layout()
    return fig

COCO_CLASSES = [
    'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
    'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
    'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
    'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
    'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
    'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
    'hair drier', 'toothbrush'
]

def read_yolo_boxes(file_path):
    boxes = []
    with open(file_path, 'r') as f:
        for line in f:
            parts = line.strip().split()
            class_name = COCO_CLASSES[int(parts[0])]
            x, y, w, h = map(float, parts[1:5])
            boxes.append((class_name, x, y, w, h))
    return boxes

import gradio as gr
import cv2
import numpy as np
import os
import matplotlib.pyplot as plt


def analyze_image(image):
    # Convert PIL Image to numpy array
    image = np.array(image)
    
    # Convert RGB to BGR (OpenCV format)
    image_bgr = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    
    img_height, img_width = image.shape[:2]
    
    # Save the uploaded image temporarily
    temp_image_path = "temp_image.jpg"
    cv2.imwrite(temp_image_path, image_bgr)
    
    # Run YOLO models
    run_yolo_models1(temp_image_path)
    label_path = 'runs/predict-seg/yolov9_c_640_detect/labels/temp_image.txt'
    label_path2 = 'runs/detect/yolov9_c_640_detect/labels/temp_image.txt'
    
    segment = extract_class_0_coordinates(label_path)
    yolo_boxes = read_yolo_boxes(label_path2)
    threshold = 10  # Set threshold (in pixels)
    
    fig = plot_boxes_and_segment(image, yolo_boxes, segment, img_width, img_height, threshold)
    
    results = []
    for class_name, x, y, w, h in yolo_boxes:
        result = box_segment_relationship((0, x, y, w, h), segment, img_width, img_height, threshold)
        results.append(f"{class_name} at ({x:.2f}, {y:.2f}) is {result} the segment.")
    
    # Clean up temporary files
    os.remove(temp_image_path)
    os.remove(label_path)
    os.remove(label_path2)
    
    return fig, "\n".join(results)

iface = gr.Interface(
    fn=analyze_image,
    inputs=gr.Image(),
    outputs=[
        gr.Plot(label="Analysis Visualization"),
        gr.Textbox(label="Analysis Results")
    ],
    title="Train obstruction detection",
    description="Upload an image to run analysis."
)

if __name__ == "__main__":
    iface.launch()